Dbpedia Based Factual Questions Answering System

Total Page:16

File Type:pdf, Size:1020Kb

Dbpedia Based Factual Questions Answering System IADIS International Journal on WWW/Internet Vol. 15, No. 1, pp. 80-95 ISSN: 1645-7641 DBPEDIA BASED FACTUAL QUESTIONS ANSWERING SYSTEM Maksym Ketsmur1, Mário Rodrigues2 and António Teixeira1 1Department of Electronics Telecommunications and Informatics / IEETA, University of Aveiro. Portugal 2Águeda School of Technology and Management / IEETA, University of Aveiro. Portugal ABSTRACT The creation of generic natural language query and answering (QA) systems is an active goal of the Semantic Web since it would allow people to conduct any query using their native language. Current solutions already handle factual questions mostly in English. The aim of this work was to develop a QA system to query knowledge bases (KB) such as DBpedia, in a first version, using factual questions in Portuguese, and in a second version, factual questions in English, French and German. This involves representing queries in terms of the KB ontology using SPARQL. The process of constructing a SPARQL query representing the natural language input involves determining: (1) the type of answer that is being sought - a person, a place, etc. - which is done by looking at the wh-words of wh-questions; (2) the main topic of the question - which person, place, etc. - obtained by morphosyntactic analysis to discover the potential subjects of the question; and (3) the properties that can be mapped to the KB ontology for creating a SPARQL query as precise as possible. The first version of the system, working for Portuguese, was tested by with 22 questions without guarantee that the answer was in the KB, and the multilingual version was tested with 30 random questions from QALD 7 (Question Answering over Linked Data) training set. The correctness of the answers was verified as well if the answer exists in the KB when the system did not produced results. A correct answer was produced for 67% of the questions for the Portuguese version and up to 55% (for English) of times for multi-language version considering that the answer existed in the KB. Results show that this approach is promising and further investigation should be done to improve it. The robustness observed, and capability to handle several languages, fosters future work to expand the system to answer questions of other types. KEYWORDS Question Answering, Multi-lingual, Knowledge Base 80 DBPEDIA BASED FACTUAL QUESTIONS ANSWERING SYSTEM 1. INTRODUCTION The predominant form of search on the internet is the use of keywords. However, the use of this form of information search is often inadvertent to express the true intention of the user (Song, D. et al., 2015). The traditional keyword searching returns an extensive list of possible results, where the user must spend some time to find the desired information. On one hand, a greater amount of information allows users to compare results and convey some conclusion, yet, it makes the search more difficult due to the quantity and growth of online information nowadays. So, systems that allow anyone to perform structured search become increasingly needed (Hirschman, L. et al., 2001; Navigli, R. et al., 2012). Using a well-structured search allows to better infer users' intent, returning the desired answer and not a list of documents as in traditional approaches. With this, a need to develop semantic search systems arise. Such systems are intended to allow users carrying out structured searches using natural language, and should identify users' intentions, generating formal semantic representations that are able to combine distinct sources of information to obtain an answer. Increasingly, the information is provided in the form of Linked Data, which consists of using the Web to interconnect different sources of information. These can be as diverse as the databases of two distinct organizations in different geographic locations. Technically, Linked Data refers to data published on the Internet in a way that can be understood by both humans and computers (Damljanovic, D. et al., 2011; Unger, C. et al., 2012). Semantic web data is published in Resource Description Framework (RDF) form, which is a standard for expressing data graphs and sharing them with other people and, perhaps more importantly, with machines. A large collection of tools and services emerged around the RDF (Bizer, C. et al., 2009; Segaran, T. et al., 2009). RDF is a language to express data models using triples, which are constituted by subject, predicate, and object. In addition, it adds several important concepts that make these models more accurate and robust, removing the ambiguity when transmitting semantic data between machines (Segaran, T. et al., 2009). The main goal of this study is to develop two versions of a QA system that allows users to get the desired information using natural language as a query. The characteristic points of this system are the use of Portuguese language in the first version, being expanded to handle English, French, and German languages in the second version, and being designed to operate directly over already existing knowledge bases (KB), being for the moment instantiated in the popular DBpedia. The paper continues in section two with the background and the relevant related work. The third section explains how the two version of QA system works and the fourth section shows representative results of each version and discusses them. The paper ends with the conclusions in section 5. 2. BACKGROUND AND RELATED WORK The first step in the development of QA systems is to understand how users search information and what kind of answer they expect (Hirschman, L. et al., 2001). Different types of questions can be asked and can be identified per the type of answer: factual, opinion, and abstract (Hirschman, L. et al., 2001). The different types of questions can be done in different 81 IADIS International Journal on WWW/Internet ways, such as indirect requests or even commands. “I would like to list all presidents of Portugal” is considered as an indirect request and “Name all presidents of Portugal” is considered as a command (Hirschman, L. et al., 2001). However, this can bring some difficulties to systems that heavily depend on identifying terms such as Who, Where, When and What in users' queries. For example, by identifying the word Who in the query, the system will determinate that the user wants to know about some human or organization, or the word Where that will indicate that the answer will be about some location. These types of systems cannot respond to the questions asked in indirect request form or even commands. Also, the user is not expected to perform search in a structured way, which in this case makes the autosuggest a good feature during the construction of the query, as seen in the TR Discover system. Not all types of questions are similar, there is evidence that some types are more difficult than others, such as Why and How tend to be more difficult to analyze because they require understanding of text and relations between entities (Hirschman, L. et al., 2001). The identification of the correct expected answer type reduces the number of possible answers, making the system more efficient and precise (Breck, E. et al., 2000). Different systems use distinct approaches to form the answer that is shown to the user. Answers can be formed in two ways, extraction or generation. In the first, the fragment that contains the answer is extracted from the original document and presented to user, while in the second the answer is extracted from multiple sentences or from several documents (Hirschman, L. et al., 2001). The ability of identifying users’ intention implies a natural language analysis where the main challenge is to understand the users’ intent that may be ambiguous. In addition, natural language processing aims to achieve a natural language analysis like humans, using different techniques that allow to identify entities, actions, relation between entities, etc. in a natural language sentence (Hirschman, L. et al., 2001; E. Liddy. et al., 2001). Many evaluations of semantic search systems referred that users prefer to use free natural language during the search rather than controlled inputs or view-based searches. Although the flexibility offered by this approach is a significant advantage, it can also become very complex (Kumar, A. et al., 2016). Allowing users full freedom in choosing terms increases the difficulty of these tools to disambiguate the search and understand the users’ intent (Elbedweihy, K. et al., 2013). Word sense disambiguation aims to understand what the terms mean. While for humans it is easy to understand the meaning of a word, for a machine it is a difficult task (Guha, R., et al., 2003; Lopes, L.S. et al. 2005; Elbedweihy, K. et al., 2013). Therefore, the use of semantic search tools is essential to match the document content with users’ intention (Hoffart, J. et al., 2011). Semantic search systems adopt different search approaches, ranging from natural language (free or guided) to visualization-based interfaces (forms or graphs). Each of these strategies provides different levels of user flexibility, query language expression and support during the query formulation (Elbedweihy, K. et al., 2013). However, as mentioned earlier, flexibility makes it difficult to map terms with concepts, properties and ontological entities. One of these difficulties is polysemy (a word with more than one meaning) and synonymy (multiple words with the same meaning). While the first affects accuracy by providing false correspondences, the second affects recall by causing the lack of true semantic correspondences. In this way, both use the word disambiguation techniques (Elbedweihy, K. et al., 2013). For example, to answer the question “How tall is ...?”, the query term tall needs to be mapped to the height property in the ontology. However, the term tall is polysemous and has different meanings including (from WordNet): "Great in vertical dimension", "High in stature", "Tall people", "Tall buildings", etc.
Recommended publications
  • How Do BERT Embeddings Organize Linguistic Knowledge?
    How Do BERT Embeddings Organize Linguistic Knowledge? Giovanni Puccettiy , Alessio Miaschi? , Felice Dell’Orletta y Scuola Normale Superiore, Pisa ?Department of Computer Science, University of Pisa Istituto di Linguistica Computazionale “Antonio Zampolli”, Pisa ItaliaNLP Lab – www.italianlp.it [email protected], [email protected], [email protected] Abstract et al., 2019), we proposed an in-depth investigation Several studies investigated the linguistic in- aimed at understanding how the information en- formation implicitly encoded in Neural Lan- coded by BERT is arranged within its internal rep- guage Models. Most of these works focused resentation. In particular, we defined two research on quantifying the amount and type of in- questions, aimed at: (i) investigating the relation- formation available within their internal rep- ship between the sentence-level linguistic knowl- resentations and across their layers. In line edge encoded in a pre-trained version of BERT and with this scenario, we proposed a different the number of individual units involved in the en- study, based on Lasso regression, aimed at understanding how the information encoded coding of such knowledge; (ii) understanding how by BERT sentence-level representations is ar- these sentence-level properties are organized within ranged within its hidden units. Using a suite of the internal representations of BERT, identifying several probing tasks, we showed the existence groups of units more relevant for specific linguistic of a relationship between the implicit knowl- tasks. We defined a suite of probing tasks based on edge learned by the model and the number of a variable selection approach, in order to identify individual units involved in the encodings of which units in the internal representations of BERT this competence.
    [Show full text]
  • Treebanks, Linguistic Theories and Applications Introduction to Treebanks
    Treebanks, Linguistic Theories and Applications Introduction to Treebanks Lecture One Petya Osenova and Kiril Simov Sofia University “St. Kliment Ohridski”, Bulgaria Bulgarian Academy of Sciences, Bulgaria ESSLLI 2018 30th European Summer School in Logic, Language and Information (6 August – 17 August 2018) Plan of the Lecture • Definition of a treebank • The place of the treebank in the language modeling • Related terms: parsebank, dynamic treebank • Prerequisites for the creation of a treebank • Treebank lifecycle • Theory (in)dependency • Language (in)dependency • Tendences in the treebank development 30th European Summer School in Logic, Language and Information (6 August – 17 August 2018) Treebank Definition A corpus annotated with syntactic information • The information in the annotation is added/checked by a trained annotator - manual annotation • The annotation is complete - no unannotated fragments of the text • The annotation is consistent - similar fragments are analysed in the same way • The primary format of annotation - syntactic tree/graph 30th European Summer School in Logic, Language and Information (6 August – 17 August 2018) Example Syntactic Trees from Wikipedia The two main approaches to modeling the syntactic information 30th European Summer School in Logic, Language and Information (6 August – 17 August 2018) Pros vs. Cons (Handbook of NLP, p. 171) Constituency • Easy to read • Correspond to common grammatical knowledge (phrases) • Introduce arbitrary complexity Dependency • Flexible • Also correspond to common grammatical
    [Show full text]
  • Knowledge Graphs on the Web – an Overview Arxiv:2003.00719V3 [Cs
    January 2020 Knowledge Graphs on the Web – an Overview Nicolas HEIST, Sven HERTLING, Daniel RINGLER, and Heiko PAULHEIM Data and Web Science Group, University of Mannheim, Germany Abstract. Knowledge Graphs are an emerging form of knowledge representation. While Google coined the term Knowledge Graph first and promoted it as a means to improve their search results, they are used in many applications today. In a knowl- edge graph, entities in the real world and/or a business domain (e.g., people, places, or events) are represented as nodes, which are connected by edges representing the relations between those entities. While companies such as Google, Microsoft, and Facebook have their own, non-public knowledge graphs, there is also a larger body of publicly available knowledge graphs, such as DBpedia or Wikidata. In this chap- ter, we provide an overview and comparison of those publicly available knowledge graphs, and give insights into their contents, size, coverage, and overlap. Keywords. Knowledge Graph, Linked Data, Semantic Web, Profiling 1. Introduction Knowledge Graphs are increasingly used as means to represent knowledge. Due to their versatile means of representation, they can be used to integrate different heterogeneous data sources, both within as well as across organizations. [8,9] Besides such domain-specific knowledge graphs which are typically developed for specific domains and/or use cases, there are also public, cross-domain knowledge graphs encoding common knowledge, such as DBpedia, Wikidata, or YAGO. [33] Such knowl- edge graphs may be used, e.g., for automatically enriching data with background knowl- arXiv:2003.00719v3 [cs.AI] 12 Mar 2020 edge to be used in knowledge-intensive downstream applications.
    [Show full text]
  • Senserelate::Allwords - a Broad Coverage Word Sense Tagger That Maximizes Semantic Relatedness
    WordNet::SenseRelate::AllWords - A Broad Coverage Word Sense Tagger that Maximizes Semantic Relatedness Ted Pedersen and Varada Kolhatkar Department of Computer Science University of Minnesota Duluth, MN 55812 USA tpederse,kolha002 @d.umn.edu http://senserelate.sourceforge.net{ } Abstract Despite these difficulties, word sense disambigua- tion is often a necessary step in NLP and can’t sim- WordNet::SenseRelate::AllWords is a freely ply be ignored. The question arises as to how to de- available open source Perl package that as- velop broad coverage sense disambiguation modules signs a sense to every content word (known that can be deployed in a practical setting without in- to WordNet) in a text. It finds the sense of vesting huge sums in manual annotation efforts. Our each word that is most related to the senses answer is WordNet::SenseRelate::AllWords (SR- of surrounding words, based on measures found in WordNet::Similarity. This method is AW), a method that uses knowledge already avail- shown to be competitive with results from re- able in the lexical database WordNet to assign senses cent evaluations including SENSEVAL-2 and to every content word in text, and as such offers SENSEVAL-3. broad coverage and requires no manual annotation of training data. SR-AW finds the sense of each word that is most 1 Introduction related or most similar to those of its neighbors in the Word sense disambiguation is the task of assigning sentence, according to any of the ten measures avail- a sense to a word based on the context in which it able in WordNet::Similarity (Pedersen et al., 2004).
    [Show full text]
  • Detecting Personal Life Events from Social Media
    Open Research Online The Open University’s repository of research publications and other research outputs Detecting Personal Life Events from Social Media Thesis How to cite: Dickinson, Thomas Kier (2019). Detecting Personal Life Events from Social Media. PhD thesis The Open University. For guidance on citations see FAQs. c 2018 The Author https://creativecommons.org/licenses/by-nc-nd/4.0/ Version: Version of Record Link(s) to article on publisher’s website: http://dx.doi.org/doi:10.21954/ou.ro.00010aa9 Copyright and Moral Rights for the articles on this site are retained by the individual authors and/or other copyright owners. For more information on Open Research Online’s data policy on reuse of materials please consult the policies page. oro.open.ac.uk Detecting Personal Life Events from Social Media a thesis presented by Thomas K. Dickinson to The Department of Science, Technology, Engineering and Mathematics in partial fulfilment of the requirements for the degree of Doctor of Philosophy in the subject of Computer Science The Open University Milton Keynes, England May 2019 Thesis advisor: Professor Harith Alani & Dr Paul Mulholland Thomas K. Dickinson Detecting Personal Life Events from Social Media Abstract Social media has become a dominating force over the past 15 years, with the rise of sites such as Facebook, Instagram, and Twitter. Some of us have been with these sites since the start, posting all about our personal lives and building up a digital identify of ourselves. But within this myriad of posts, what actually matters to us, and what do our digital identities tell people about ourselves? One way that we can start to filter through this data, is to build classifiers that can identify posts about our personal life events, allowing us to start to self reflect on what we share online.
    [Show full text]
  • Deep Linguistic Analysis for the Accurate Identification of Predicate
    Deep Linguistic Analysis for the Accurate Identification of Predicate-Argument Relations Yusuke Miyao Jun'ichi Tsujii Department of Computer Science Department of Computer Science University of Tokyo University of Tokyo [email protected] CREST, JST [email protected] Abstract obtained by deep linguistic analysis (Gildea and This paper evaluates the accuracy of HPSG Hockenmaier, 2003; Chen and Rambow, 2003). parsing in terms of the identification of They employed a CCG (Steedman, 2000) or LTAG predicate-argument relations. We could directly (Schabes et al., 1988) parser to acquire syntac- compare the output of HPSG parsing with Prop- tic/semantic structures, which would be passed to Bank annotations, by assuming a unique map- statistical classifier as features. That is, they used ping from HPSG semantic representation into deep analysis as a preprocessor to obtain useful fea- PropBank annotation. Even though PropBank tures for training a probabilistic model or statistical was not used for the training of a disambigua- tion model, an HPSG parser achieved the ac- classifier of a semantic argument identifier. These curacy competitive with existing studies on the results imply the superiority of deep linguistic anal- task of identifying PropBank annotations. ysis for this task. Although the statistical approach seems a reason- 1 Introduction able way for developing an accurate identifier of Recently, deep linguistic analysis has successfully PropBank annotations, this study aims at establish- been applied to real-world texts. Several parsers ing a method of directly comparing the outputs of have been implemented in various grammar for- HPSG parsing with the PropBank annotation in or- malisms and empirical evaluation has been re- der to explicitly demonstrate the availability of deep ported: LFG (Riezler et al., 2002; Cahill et al., parsers.
    [Show full text]
  • The Procedure of Lexico-Semantic Annotation of Składnica Treebank
    The Procedure of Lexico-Semantic Annotation of Składnica Treebank Elzbieta˙ Hajnicz Institute of Computer Science, Polish Academy of Sciences ul. Ordona 21, 01-237 Warsaw, Poland [email protected] Abstract In this paper, the procedure of lexico-semantic annotation of Składnica Treebank using Polish WordNet is presented. Other semantically annotated corpora, in particular treebanks, are outlined first. Resources involved in annotation as well as a tool called Semantikon used for it are described. The main part of the paper is the analysis of the applied procedure. It consists of the basic and correction phases. During basic phase all nouns, verbs and adjectives are annotated with wordnet senses. The annotation is performed independently by two linguists. Multi-word units obtain special tags, synonyms and hypernyms are used for senses absent in Polish WordNet. Additionally, each sentence receives its general assessment. During the correction phase, conflicts are resolved by the linguist supervising the process. Finally, some statistics of the results of annotation are given, including inter-annotator agreement. The final resource is represented in XML files preserving the structure of Składnica. Keywords: treebanks, wordnets, semantic annotation, Polish 1. Introduction 2. Semantically Annotated Corpora It is widely acknowledged that linguistically annotated cor- Semantic annotation of text corpora seems to be the last pora play a crucial role in NLP. There is even a tendency phase in the process of corpus annotation, less popular than towards their ever-deeper annotation. In particular, seman- morphosyntactic and (shallow or deep) syntactic annota- tically annotated corpora become more and more popular tion. However, there exist semantically annotated subcor- as they have a number of applications in word sense disam- pora for many languages.
    [Show full text]
  • Unified Language Model Pre-Training for Natural
    Unified Language Model Pre-training for Natural Language Understanding and Generation Li Dong∗ Nan Yang∗ Wenhui Wang∗ Furu Wei∗† Xiaodong Liu Yu Wang Jianfeng Gao Ming Zhou Hsiao-Wuen Hon Microsoft Research {lidong1,nanya,wenwan,fuwei}@microsoft.com {xiaodl,yuwan,jfgao,mingzhou,hon}@microsoft.com Abstract This paper presents a new UNIfied pre-trained Language Model (UNILM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirec- tional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UNILM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UNILM achieves new state-of- the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40.51 (2.04 absolute improvement), the Gigaword abstractive summarization ROUGE-L to 35.75 (0.86 absolute improvement), the CoQA generative question answering F1 score to 82.5 (37.1 absolute improvement), the SQuAD question generation BLEU-4 to 22.12 (3.75 absolute improvement), and the DSTC7 document-grounded dialog response generation NIST-4 to 2.67 (human performance is 2.65). The code and pre-trained models are available at https://github.com/microsoft/unilm. 1 Introduction Language model (LM) pre-training has substantially advanced the state of the art across a variety of natural language processing tasks [8, 29, 19, 31, 9, 1].
    [Show full text]
  • Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation
    Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation Alexander Panchenkoz, Fide Martenz, Eugen Ruppertz, Stefano Faralliy, Dmitry Ustalov∗, Simone Paolo Ponzettoy, and Chris Biemannz zLanguage Technology Group, Department of Informatics, Universitat¨ Hamburg, Germany yWeb and Data Science Group, Department of Informatics, Universitat¨ Mannheim, Germany ∗Institute of Natural Sciences and Mathematics, Ural Federal University, Russia fpanchenko,marten,ruppert,[email protected] fsimone,[email protected] [email protected] Abstract manually in one of the underlying resources, such as Wikipedia. Unsupervised knowledge-free ap- Interpretability of a predictive model is proaches, e.g. (Di Marco and Navigli, 2013; Bar- a powerful feature that gains the trust of tunov et al., 2016), require no manual labor, but users in the correctness of the predictions. the resulting sense representations lack the above- In word sense disambiguation (WSD), mentioned features enabling interpretability. For knowledge-based systems tend to be much instance, systems based on sense embeddings are more interpretable than knowledge-free based on dense uninterpretable vectors. Therefore, counterparts as they rely on the wealth of the meaning of a sense can be interpreted only on manually-encoded elements representing the basis of a list of related senses. word senses, such as hypernyms, usage We present a system that brings interpretability examples, and images. We present a WSD of the knowledge-based sense representations into system that bridges the gap between these the world of unsupervised knowledge-free WSD two so far disconnected groups of meth- models. The contribution of this paper is the first ods. Namely, our system, providing access system for word sense induction and disambigua- to several state-of-the-art WSD models, tion, which is unsupervised, knowledge-free, and aims to be interpretable as a knowledge- interpretable at the same time.
    [Show full text]
  • Building a Treebank for French
    Building a treebank for French £ £¥ Anne Abeillé£ , Lionel Clément , Alexandra Kinyon ¥ £ TALaNa, Université Paris 7 University of Pennsylvania 75251 Paris cedex 05 Philadelphia FRANCE USA abeille, clement, [email protected] Abstract Very few gold standard annotated corpora are currently available for French. We present an ongoing project to build a reference treebank for French starting with a tagged newspaper corpus of 1 Million words (Abeillé et al., 1998), (Abeillé and Clément, 1999). Similarly to the Penn TreeBank (Marcus et al., 1993), we distinguish an automatic parsing phase followed by a second phase of systematic manual validation and correction. Similarly to the Prague treebank (Hajicova et al., 1998), we rely on several types of morphosyntactic and syntactic annotations for which we define extensive guidelines. Our goal is to provide a theory neutral, surface oriented, error free treebank for French. Similarly to the Negra project (Brants et al., 1999), we annotate both constituents and functional relations. 1. The tagged corpus pronoun (= him ) or a weak clitic pronoun (= to him or to As reported in (Abeillé and Clément, 1999), we present her), plus can either be a negative adverb (= not any more) the general methodology, the automatic tagging phase, the or a simple adverb (= more). Inflectional morphology also human validation phase and the final state of the tagged has to be annotated since morphological endings are impor- corpus. tant for gathering constituants (based on agreement marks) and also because lots of forms in French are ambiguous 1.1. Methodology with respect to mode, person, number or gender. For exam- 1.1.1.
    [Show full text]
  • Ten Years of Babelnet: a Survey
    Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21) Survey Track Ten Years of BabelNet: A Survey Roberto Navigli1 , Michele Bevilacqua1 , Simone Conia1 , Dario Montagnini2 and Francesco Cecconi2 1Sapienza NLP Group, Sapienza University of Rome, Italy 2Babelscape, Italy froberto.navigli, michele.bevilacqua, [email protected] fmontagnini, [email protected] Abstract to integrate symbolic knowledge into neural architectures [d’Avila Garcez and Lamb, 2020]. The rationale is that the The intelligent manipulation of symbolic knowl- use of, and linkage to, symbolic knowledge can not only en- edge has been a long-sought goal of AI. How- able interpretable, explainable and accountable AI systems, ever, when it comes to Natural Language Process- but it can also increase the degree of generalization to rare ing (NLP), symbols have to be mapped to words patterns (e.g., infrequent meanings) and promote better use and phrases, which are not only ambiguous but also of information which is not explicit in the text. language-specific: multilinguality is indeed a de- Symbolic knowledge requires that the link between form sirable property for NLP systems, and one which and meaning be made explicit, connecting strings to repre- enables the generalization of tasks where multiple sentations of concepts, entities and thoughts. Historical re- languages need to be dealt with, without translat- sources such as WordNet [Miller, 1995] are important en- ing text. In this paper we survey BabelNet, a pop- deavors which systematize symbolic knowledge about the ular wide-coverage lexical-semantic knowledge re- words of a language, i.e., lexicographic knowledge, not only source obtained by merging heterogeneous sources in a machine-readable format, but also in structured form, into a unified semantic network that helps to scale thanks to the organization of concepts into a semantic net- tasks and applications to hundreds of languages.
    [Show full text]
  • Converting an HPSG-Based Treebank Into Its Parallel Dependency-Based Treebank
    Converting an HPSG-based Treebank into its Parallel Dependency-based Treebank Masood Ghayoomiy z Jonas Kuhnz yDepartment of Mathematics and Computer Science, Freie Universität Berlin z Institute for Natural Language Processing, University of Stuttgart [email protected] [email protected] Abstract A treebank is an important language resource for supervised statistical parsers. The parser induces the grammatical properties of a language from this language resource and uses the model to parse unseen data automatically. Since developing such a resource is very time-consuming and tedious, one can take advantage of already extant resources by adapting them to a particular application. This reduces the amount of human effort required to develop a new language resource. In this paper, we introduce an algorithm to convert an HPSG-based treebank into its parallel dependency-based treebank. With this converter, we can automatically create a new language resource from an existing treebank developed based on a grammar formalism. Our proposed algorithm is able to create both projective and non-projective dependency trees. Keywords: Treebank Conversion, the Persian Language, HPSG-based Treebank, Dependency-based Treebank 1. Introduction treebank is introduced in Section 4. The properties Supervised statistical parsers require a set of annotated of the available dependency treebanks for Persian and data, called a treebank, to learn the grammar of the their pros and cons are explained in Section 5. The target language and create a wide coverage grammar tools and the experimental setup as well as the ob- model to parse unseen data. Developing such a data tained results are described and discussed in Section source is a tedious and time-consuming task.
    [Show full text]